Commit graph

2385 commits

Author SHA1 Message Date
tomoya-kawaguchi
cd96f6b911 chore: organize comments 2025-05-29 13:03:21 +09:00
tomoya-kawaguchi
1955157e9a feat: add AWS Secrets Manager Integration 2025-05-29 12:42:05 +09:00
Judy
8c7c087931 feat: TODO multi-line 2025-05-28 21:33:28 +09:00
Tal
d5f77560e3
Merge pull request #1811 from loolootech/feature/gitea-implement
[Feature] - Gitea implement
2025-05-28 08:22:16 +03:00
Tal
6f27fc9271
Merge pull request #1828 from Akileox/refactor-langchain-handler
Refactor: Enhance AI Handler Robustness, Interface Compliance, and Asynchronous Operations (Resolves #1784)
2025-05-28 08:20:04 +03:00
Judy
53b913a4cb refactor: add TypedDict and type hints to todo item formatter 2025-05-27 17:52:36 +09:00
Judy
7d38814cae refactor: Change error messsage 'print' -> 'get_logger' 2025-05-27 16:51:38 +09:00
Judy
08440d8ebd feat: Add <details> to TODO sections 2025-05-27 16:19:19 +09:00
Judy
bab8ee9633 modify: ToDo -> TODO 2025-05-27 16:08:33 +09:00
Akileo
e8ace9fcf9 change type check and remove useless sync 2025-05-26 14:52:45 +09:00
Tal
a128db8393
Merge pull request #1822 from PeterDaveHelloKitchen/Gemini-2.5-Flash
Complete Gemini 2.5 Flash model info
2025-05-26 07:48:33 +03:00
Pinyoo Thotaboot
b18a509120 Use current 2025-05-26 11:44:39 +07:00
Pinyoo Thotaboot
6063bf5978 Check is tempolary before remove it 2025-05-26 11:42:09 +07:00
Pinyoo Thotaboot
5d105c64d2 Rename & Return comment object after published 2025-05-26 11:40:29 +07:00
Pinyoo Thotaboot
f06ee951d7 Change raise runtime error 2025-05-26 11:36:49 +07:00
Pinyoo Thotaboot
b264f42e3d Fixed handle verify signature when has failed 2025-05-26 11:31:40 +07:00
Pinyoo Thotaboot
a975b32376 Get empty content when exception 2025-05-26 11:26:16 +07:00
Pinyoo Thotaboot
5e9c56b96c Remove the unnecessary flag '--pr_description.final_update_message=false' 2025-05-26 11:05:58 +07:00
Pinyoo Thotaboot
f78762cf2e Change the default value of is 2025-05-26 11:04:11 +07:00
Pinyoo Thotaboot
4a019ba7c4 Merge branch 'main' of github.com:qodo-ai/pr-agent into feature/gitea-implement 2025-05-26 10:59:19 +07:00
mrT23
16d980ec76
fix: update Mermaid diagram instructions for clarity and consistency 2025-05-25 15:38:08 +03:00
mrT23
2eeb9b0411
fix: improve Mermaid diagram formatting and instructions in PR description template 2025-05-25 14:59:18 +03:00
mrT23
f3cb4e8384
fix: ensure proper formatting of changes_diagram in PR description output 2025-05-25 14:32:12 +03:00
Tal
946657a6d1
Merge pull request #1824 from OSSCA-2025-Egg-Benedict/feature/sequence-diagram
Improve/describe tool documentation and make add_diagram feature opt-in by default
2025-05-25 13:44:53 +03:00
chilln
d5dead5c7f refactor: moved diagram logic to 'changes_diagram' in PRDescription and updated prompt for clarity 2025-05-25 18:37:28 +09:00
chilln
6aac41a0df refactor:rename to 2025-05-25 18:27:03 +09:00
Tal
2453508023
Merge pull request #1805 from group-3-sPRinter/improve/token_handler
Refactor count_tokens method structure in token_handler.py for better extensibility
2025-05-25 12:11:41 +03:00
kkan9ma
84f2f4fe3d Fix: use ModelTypeValidator static methods directly 2025-05-25 18:00:38 +09:00
Akileo
ff52ae9281 add img_path and _create_chat_async 2025-05-25 15:34:50 +09:00
Akileo
d791e9f3d1 Fix: Improve langchain import error handling and add img_path to handler
Addresses issue #1784:
- Raises ImportError if langchain is not installed when LangChainOpenAIHandler is initialized.
- Adds img_path parameter to LangChainOpenAIHandler.chat_completion for interface consistency.
- Logs a warning if img_path is used with LangChainOpenAIHandler.
2025-05-25 15:28:18 +09:00
mrT23
18a8a741fa
ensure_ticket_compliance 2025-05-25 08:31:24 +03:00
Tal
4cdaad1fc5
Merge pull request #1816 from TaskerJang/feature/clip-tokens-tests-and-docs
Add Unit Tests and Improve Documentation for utils.py clip_tokens Function
2025-05-25 08:18:26 +03:00
chilln
e57d3101e4 fix:set parameter default to false to make the feature opt-in by design 2025-05-25 12:48:29 +09:00
chilln
f58c40a6ae refactor: replace single quotes with double quotes to match existing code style 2025-05-25 12:48:13 +09:00
chilln
d8aa61622f
Merge pull request #5 from OSSCA-2025-Egg-Benedict/yeji
feat: conditionally append Mermaid sequence diagram instruction in prompt
2025-05-25 12:15:01 +09:00
chilln
2b2818a435
Merge pull request #4 from OSSCA-2025-Egg-Benedict/seonwoong
feat: add add_diagram configuration option to PR description
2025-05-25 12:13:50 +09:00
chilln
cdca5a55b2
Merge pull request #2 from OSSCA-2025-Egg-Benedict/yujin
feat: add add_diagram flag in configuration.toml
2025-05-25 12:06:31 +09:00
isExample
3a385b62d6 feat: conditionally append Mermaid sequence diagram instruction in pr_description prompt 2025-05-25 11:51:22 +09:00
ssunbear
5a0affd6cb feat: add add_diagram configuration option to PR description 2025-05-25 11:08:52 +09:00
yujindonut
d62cbb2fc4 feat: add add_diagram flag in configuration.toml 2025-05-25 10:28:50 +09:00
Peter Dave Hello
4047e71268 Complete Gemini 2.5 Flash model info 2025-05-24 23:52:18 +08:00
joosomi
ca3df352ab refactor: improve todo section handling and clarify todo content description 2025-05-25 00:02:21 +09:00
soprue
16b9ccd025 feat: conditionally include diagram in output example 2025-05-24 23:43:16 +09:00
Tal
43dbe24a7f
Merge pull request #1817 from PeterDaveHelloKitchen/Grok-3
Add Grok-3 non-beta model IDs
2025-05-24 16:32:50 +03:00
Tal
f4a9bc3de7
Merge pull request #1814 from hirobf10/support-claude-4
feat: add support for Claude 4 family
2025-05-24 16:29:48 +03:00
Tal
20b1a1f552
Merge pull request #1808 from group-3-sPRinter/fix/retry-exclude-rate-limit-error
fix: exclude RateLimitError from `@retry` in `AIHandler.chat_completion()`
2025-05-24 16:14:25 +03:00
Tal
4c98cffd37
Merge pull request #1801 from darkdread/main
docs: include [aws] in .secrets.template
2025-05-24 16:12:52 +03:00
dst03106
b83085ea00 fix: remove whitespace from relevant file 2025-05-24 22:01:29 +09:00
Peter Dave Hello
95c94b80a2 Add Grok-3 non-beta model IDs 2025-05-24 14:22:55 +08:00
TaskerJang
e2586cb64a docs: improve clip_tokens function docstring and add examples 2025-05-24 10:46:58 +09:00
Hiroyuki Otomo
1f836e405d fix: reflect comments 2025-05-24 09:45:27 +09:00
joosomi
66131854c1 fix: avoid incorrect ToDo header 2025-05-24 03:04:59 +09:00
joosomi
788c0c12e6 feat: add TODO comments to PR review output 2025-05-24 01:52:52 +09:00
Hiroyuki Otomo
10703a9098 feat: add support for Claude 4 2025-05-23 14:16:44 +09:00
Pinyoo Thotaboot
162cc9d833 Fixed error propagation 2025-05-22 15:06:35 +07:00
Pinyoo Thotaboot
0f893bc492 Fixed webhook security concern 2025-05-22 15:03:15 +07:00
Pinyoo Thotaboot
000f0ba93e Fixed ensure SHA 2025-05-22 15:01:08 +07:00
Pinyoo Thotaboot
48c29c9ffa Add null check 2025-05-22 14:59:29 +07:00
Pinyoo Thotaboot
930cd69909 Fixed conflicts 2025-05-22 14:54:26 +07:00
Kangmoon Seo
466ec4ce90 fix: exclude RateLimitError from retry logic 2025-05-22 15:04:16 +09:00
kkan9ma
facfb5f46b Add missing code: use_context=False 2025-05-22 13:32:20 +09:00
kkan9ma
cc686ef26d Reorder model check: OpenAI before Anthropic
OpenAI is the default in most cases, so checking it first skips unnecessary Anthropic logic.
2025-05-22 13:12:04 +09:00
kkan9ma
ead7491ca9 Apply convention for marking private 2025-05-21 18:08:48 +09:00
kkan9ma
df0355d827 Remove member variable for restroring get_settings() 2025-05-21 18:07:47 +09:00
kkan9ma
c3ea048b71 Restore original return logic for force_accurate condition 2025-05-21 17:52:51 +09:00
kkan9ma
648829b770 Rename method 2025-05-21 17:51:03 +09:00
Tal
dd17aadfe3
Merge pull request #1803 from group-3-sPRinter/fix/litellm-exception-order
fix: reorder exception handling in `LiteLLMAIHandler.chat_completion()`
2025-05-21 07:42:18 +03:00
Tal
199b463eaa
Merge pull request #1798 from seohyun-lee/docs/usage-guide
Correct typos in documentation and log messages
2025-05-21 07:38:22 +03:00
Tal
7821e71b17
Merge pull request #1787 from nicholasgribanov/feature/gitea-forgejo-support
#1657 add gitea/forgejo support
2025-05-21 07:35:31 +03:00
Kangmoon Seo
6405284461 fix: reorder exception handling to enable proper retry behavior 2025-05-20 18:22:33 +09:00
Pinyoo Thotaboot
1b74942919 Set default configuration of Gitea 2025-05-20 15:18:07 +07:00
kkan9ma
97f2b6f736 Fix TypeError 2025-05-20 15:29:27 +09:00
kkan9ma
f198e6fa09 Add constants and improve token calculation logic 2025-05-20 14:12:24 +09:00
kkan9ma
e72bb28c4e Replace get_settings() with self.settings 2025-05-20 13:50:30 +09:00
kkan9ma
81fa22e4df Add model name validation 2025-05-20 13:47:15 +09:00
Walson Low (刘维昇)
8aa89ff8e6 docs: include [aws] in .secrets.template 2025-05-20 10:27:13 +08:00
Seohyun Lee
4679dce3af refactor: Correct case typo of PR in log 2025-05-20 02:31:48 +09:00
Seohyun Lee
94aa8e8638 refactor: Correct case typo in log 2025-05-20 02:30:17 +09:00
Seohyun Lee
f5a069d6b4 refactor: Align comment formatting with others 2025-05-20 02:28:43 +09:00
Guber Tamas
5a8ce252f7 Adding num_max_findings configuration parameter with a default value of 3, to have the possibility to extend it 2025-05-19 16:16:23 +02:00
mrT23
db5138dc42
Improve YAML parsing with additional fallback strategies for AI predictions 2025-05-17 20:38:05 +03:00
Tal
9a9feb47a6
Merge pull request #1786 from qodo-ai/pr-1736
Pr 1736
2025-05-17 15:29:23 +03:00
Nikolay Gribanov
d67d07acc7 #1657 review fix 2 2025-05-16 20:30:17 +03:00
Nikolay Gribanov
12b1fe23da #1657 review fix 2025-05-16 20:12:40 +03:00
Nikolay Gribanov
f857ea1f22 #1657 add gitea/forgejo support 2025-05-16 19:43:21 +03:00
mrT23
f47da75e6f
Remove debug print statement from should_process_pr_logic function 2025-05-16 17:23:27 +03:00
mrT23
42557feb97
Enhance repository filtering with regex pattern matching for ignore_repositories 2025-05-16 17:20:54 +03:00
Tal
c15fb16528
Merge pull request #1779 from dnnspaul/main
Enable usage of OpenAI like APIs
2025-05-16 16:59:18 +03:00
Tal
d268db5f0d
Merge pull request #1778 from smartandhandsome/main
Cleanup: Remove Unused import and Fix Parameter Typo
2025-05-16 16:54:55 +03:00
mrT23
9974015682
Add Gemini-2.5-pro-preview-05-06 model and update litellm dependency 2025-05-16 16:32:45 +03:00
Pinyoo Thotaboot
fab8573c4d Set default configuration 2025-05-16 16:33:36 +07:00
Pinyoo Thotaboot
2d7636543c Implement provider 2025-05-16 16:31:49 +07:00
Pinyoo Thotaboot
cf2b95b766 Create webhook server implement for 2025-05-16 16:30:50 +07:00
Pinyoo Thotaboot
9ef0c451bf Create provider module for 2025-05-16 16:30:10 +07:00
kkan9ma
05ab5f699f Improve token calculation logic based on model type
- Rename calc_tokens to get_token_count_by_model_type for clearer intent
- Separate model type detection logic to improve maintainability
2025-05-16 17:51:22 +09:00
Dennis Paul
250870a3da enable usage of openai like apis 2025-05-15 16:05:05 +02:00
Sangmin Park
a3c9fbbf2c revert try except 2025-05-15 19:40:40 +09:00
Sangmin Park
c79b655864 Fix typo in method parameter name 2025-05-15 18:42:08 +09:00
Sangmin Park
e55fd64bda Remove unnecessary nested try-except block for cleaner code. Streamlined the import statement to remove an unused reference to get_git_provider. 2025-05-15 18:41:39 +09:00
Tal
35d75e996f
Merge pull request #1770 from dst03106/fix/add-ttl-when-callback-enabled
fix: add timeout to asyncio.wait during CLI execution to avoid hanging when callback is enabled
2025-05-13 18:33:56 +03:00
dst03106
e2af22d2a0 Log a warning for pending asyncio tasks with coroutine details 2025-05-13 17:37:09 +09:00
Yunhui Chae
d86d1ef3dc
Log a warning when there are pending asyncio tasks
Co-authored-by: qodo-merge-pro-for-open-source[bot] <189517486+qodo-merge-pro-for-open-source[bot]@users.noreply.github.com>
2025-05-13 17:34:30 +09:00
dst03106
e7317ce99f Add timeout to asyncio.wait 2025-05-13 14:46:50 +09:00
Tal
9cc6d37165
Merge pull request #1764 from twdkeule/bugfix/markdown-link-in-prompt
Changelog prompt: fix markdown link
2025-05-12 16:01:28 +03:00
Tal
bcbb3ac228
Merge pull request #1746 from twdkeule/feature/azure-devops-persistent-comment
Implement Azure Devops persistent comment
2025-05-12 15:56:12 +03:00
Thomas De Keulenaer
db0c213d72 AzureDevops webhook: allow disabling BasicAuth
Azure webhooks do not allow BasicAuth without HTTPS
2025-05-12 09:00:36 +02:00
Thomas De Keulenaer
954d61e5dc Azure: refactor publish_code_suggestions() to use azure classes 2025-05-12 09:00:36 +02:00
Thomas De Keulenaer
24a90cab8e Azure: handle inline /ask 2025-05-12 09:00:17 +02:00
Thomas De Keulenaer
67272700a6 Azure: handle line comments 2025-05-12 08:31:15 +02:00
Thomas De Keulenaer
3a07b55d0c Azure: dont start threads as active because they block the pull request 2025-05-12 08:31:15 +02:00
Thomas De Keulenaer
c924affebc Azure devops provider: add persistent comment 2025-05-12 08:31:15 +02:00
Thomas De Keulenaer
e516d66c1c Azure: return Comment object when creating comment 2025-05-12 08:31:15 +02:00
Thomas De Keulenaer
212c72eb7d Changelog prompt: fix markdown link 2025-05-12 08:26:19 +02:00
Tal
850583acb4
Merge pull request #1758 from joosomi/fix/pr-description-type-header
fix: avoid duplicate header for list types to prevent markdown break
2025-05-11 11:06:42 +03:00
joosomi
57eaba0e75 fix: ensure string conversion for list elements 2025-05-09 21:33:42 +09:00
joosomi
6062c99c47 fix: avoid duplicate header for list types to prevent markdown break 2025-05-09 21:20:04 +09:00
chilln
c357f09967 fix:correct typo in logger parameter from 'artifacts' to 'artifact' 2025-05-09 11:12:04 +09:00
Tal
36307e66f1
Merge pull request #1749 from simonstamm/main
fix(gitlab): trigger when MR changes from draft to ready
2025-05-08 19:18:53 +03:00
Tal
8bc39c0120
Merge pull request #1745 from MaxnSter/fix/extra_instruction
fix: Prevent duplicate language instructions in extra_instructions
2025-05-08 19:04:53 +03:00
Tal
f5857f0fde
Merge pull request #1744 from irfansofyana/openrouter-support
Openrouter support
2025-05-08 19:02:02 +03:00
Simon Stamm
38f00386b4
fix(gitlab): trigger when MR changes from draft to ready 2025-05-08 12:50:54 +02:00
Maxnster
a11e97b5f5 fix: Prevent duplicate language instructions in extra_instructions 2025-05-07 18:26:12 +08:00
irfan.putra
5061fb5a24 docs: add support for openrouter 2025-05-07 12:04:45 +07:00
irfan.putra
7a6a28d2b9 feat: add openrouter support in litellm 2025-05-07 11:54:07 +07:00
Thomas De Keulenaer
df1d859e54 Azure devops: parse PR url starting from the end 2025-05-06 15:01:48 +02:00
Mike Davies
d606672801 Add ignore_repositories config for PR filtering
What Changed?
* Added support to ignore PRs/MRs from specific repositories in GitHub, Bitbucket, and GitLab webhook logic
* Updated configuration.toml to include ignore_repositories option
* Added unit tests for ignore_repositories across all supported providers
2025-04-30 14:09:40 -07:00
yuli.kamakura
4ad43c48e5 Fix type hint for get_pr_description method and clean up whitespace 2025-04-28 17:59:09 +08:00
mrT23
f505c7ad3c
Add multi-model support for different reasoning tasks 2025-04-27 11:00:34 +03:00
mrT23
c951fc9a87
Improve dynamic context handling with partial line matching and adjust model configuration 2025-04-27 10:46:23 +03:00
mrT23
3f194e6730
Improve dynamic context handling in git patch processing 2025-04-27 10:07:56 +03:00
mrT23
f53bd524c5
Support multiple model types for different reasoning tasks 2025-04-27 08:50:03 +03:00
mrT23
60a887ffe1
Improve code suggestion prompts for clarity, accuracy, and evaluation criteria 2025-04-27 08:42:28 +03:00
ofir-frd
dedad94a20 Fix code indentation in get_review_thread_comments method 2025-04-24 09:34:51 +03:00
ofir-frd
5d5b57255e
Merge pull request #1687 from benedict-lee/feat/add-conversation-history-on-line-question
Improvement: Enhance ask_line tool by adding PR review comment threads as context
2025-04-24 09:32:43 +03:00
Benedict Lee
c35942c12b
mprove get_review_thread_comments method implementation
Co-authored-by: ofir-frd <85901822+ofir-frd@users.noreply.github.com>
2025-04-24 11:23:16 +09:00
Benedict Lee
ddb94ec9b4
mprove get_review_thread_comments method implementation
Co-authored-by: ofir-frd <85901822+ofir-frd@users.noreply.github.com>
2025-04-24 11:22:43 +09:00
Benedict Lee
29d4fe510e
Improve get_review_thread_comments method implementation
Co-authored-by: ofir-frd <85901822+ofir-frd@users.noreply.github.com>
2025-04-24 11:21:49 +09:00
mrT23
1aa0186f5c
Improve field descriptions for code suggestion model clarity and brevity 2025-04-22 14:19:54 +03:00
benedict.lee
9906ec3687 Improve conversation history formatting with numbered comments 2025-04-21 17:14:36 +09:00
benedict.lee
8b4bf49f1c Improve conversation history handling and prompts for line questions 2025-04-21 16:50:37 +09:00
benedict.lee
e11c2e1c7f Reorganize imports according to Python conventions 2025-04-21 16:30:27 +09:00
benedict.lee
a434d0af9b Improve comment thread retrieval by using in_reply_to_id instead of line numbers 2025-04-21 16:28:42 +09:00
mrT23
4ac0aa56e5
Update model references from o3-mini to o4-mini and add Gemini models 2025-04-19 09:26:35 +03:00
Peter Dave Hello
e854383123 Replace default o3-mini with o4-mini 2025-04-19 03:52:10 +08:00
dst03106
869a179506 feat: add support for Mistral and Codestral models 2025-04-18 14:04:59 +09:00
Peter Dave Hello
4e3e963ce5 Add OpenAI o3 & 4o-mini reasoning models
Reference:
- https://platform.openai.com/docs/models/o3
- https://platform.openai.com/docs/models/o4-mini
- https://openai.com/index/introducing-o3-and-o4-mini/
2025-04-17 02:32:14 +08:00
arpit-at
27a7c1a94f doc update and minor fix 2025-04-16 13:32:53 +05:30
arpit-at
dc46acb762 doc update and minor fix 2025-04-16 13:27:52 +05:30
arpit-at
0da667d179 support Azure AD authentication for OpenAI services for litellm implemetation 2025-04-16 11:19:04 +05:30
mrT23
3d2a285091
Add skip_ci_on_push configuration option for changelog updates 2025-04-15 19:28:36 +03:00
mrT23
08bf9593b2
Fix tokenizer fallback to use o200k_base instead of cl100k_base 2025-04-14 21:15:19 +03:00
Peter Dave Hello
57808075be Add support of OpenAI GPT-4.1 model family
Reference:
- https://openai.com/index/gpt-4-1/
- https://platform.openai.com/docs/models/gpt-4.1
2025-04-15 01:57:46 +08:00
mrT23
8bdd11646c
Fix token assignment in Bitbucket provider authentication 2025-04-12 10:07:45 +03:00
Tal
a649e323d3
Merge pull request #1683 from wirelessr/feat/issue-1681
Support Bitbucket Basic Auth
2025-04-11 14:37:56 +03:00
Chunting Wu
7a32faf64f Fix Bearer backward compatibility logic 2025-04-11 17:44:46 +08:00
Chunting Wu
5f2d4d400e Extract repeated token retrieval logic into a helper function to reduce code duplication 2025-04-11 16:20:28 +08:00
ChunTing Wu
0cbf65dab6
Update pr_agent/git_providers/bitbucket_provider.py
Co-authored-by: Prateek <110811408+Prateikx@users.noreply.github.com>
2025-04-11 14:59:27 +08:00
ChunTing Wu
c0c307503f
Update pr_agent/git_providers/bitbucket_provider.py
Co-authored-by: Prateek <110811408+Prateikx@users.noreply.github.com>
2025-04-11 14:55:06 +08:00
Tal
60ace1ed09
Merge pull request #1685 from imperorrp/add_gemini2.5preview
Add support of Gemini 2.5 Pro preview model
2025-04-11 09:54:09 +03:00
Tal
7f6014e064
Merge pull request #1684 from PeterDaveHelloKitchen/Support-xAI-Grok
Add support of xAI and their Grok-2 & Grok-3 model
2025-04-11 09:53:08 +03:00
Tal
e4f40da35c
Merge pull request #1680 from PeterDaveHelloKitchen/Add-Groq-Llama-4-scout-and-maverick-17b
Add support of Meta's Llama 4 Scout and Maverick 17b from Groq Cloud
2025-04-11 09:51:21 +03:00
Peter Dave Hello
0ac7028bc6 Support xAI Grok-3 series models
Reference:
- https://docs.x.ai/docs/release-notes#april-2025
2025-04-11 00:40:00 +08:00
benedict.lee
9c06b6b266 Apply PR review feedback: Code style and functionality improvements 2025-04-10 21:56:37 +09:00
Benedict Lee
c5165d917b
refactor: Validate all required parameters before proceeding
Co-authored-by: ofir-frd <85901822+ofir-frd@users.noreply.github.com>
2025-04-10 19:59:34 +09:00
Benedict Lee
6bf093a6a1
refactor: Add GitHub provider check for conversation history
Co-authored-by: ofir-frd <85901822+ofir-frd@users.noreply.github.com>
2025-04-10 19:41:43 +09:00
Benedict Lee
8952459f6d
Update pr_agent/tools/pr_line_questions.py
Co-authored-by: Prateek <110811408+Prateikx@users.noreply.github.com>
2025-04-10 08:48:59 +09:00
benedict.lee
b53d2773a9 improve ask_line tool(add conversation history context) 2025-04-09 23:45:04 +09:00
mrT23
526d7ff5d2
Update default number of code suggestions per chunk from 4 to 3 2025-04-09 08:24:26 +03:00
mrT23
cdc354c33b
disable dynamic variables 2025-04-08 21:07:45 +03:00
Ratish Panda
eb9c4fa110 add gemini 2.5 pro preview model token limit 2025-04-08 20:41:59 +05:30
CT Wu
ca95e876eb Enhance Bitbucket provider functionality and update secret configuration template. 2025-04-08 17:52:52 +08:00
Peter Dave Hello
83bb3b25d8 Add support of Meta's Llama 4 Scout and Maverick 17b from Groq Cloud
Reference:
- https://ai.meta.com/blog/llama-4-multimodal-intelligence/
- https://console.groq.com/docs/models#preview-models
- https://groq.com/llama-4-now-live-on-groq-build-fast-at-the-lowest-cost-without-compromise/
2025-04-08 01:47:15 +08:00
Peter Dave Hello
665fb90a98 Add support of xAI and their Grok-2 model
Close #1630
2025-04-08 01:36:21 +08:00
Peter Dave Hello
9b19fcdc90 Add support of OpenAI GPT-4.5 Preview model
Reference:
- https://openai.com/index/introducing-gpt-4-5/
- https://platform.openai.com/docs/models/gpt-4.5-preview
2025-04-04 05:13:15 +08:00
Tal
d938ff05ef
Merge pull request #1667 from jmrtnz94/1592_ENVLogLevel
Update logging configuration to use dynamic log level from settings
2025-04-04 11:31:44 +03:00
Jose Martinez
b7b533ddf6 Update azuredevops logger setup to use dynamic log level from configuration 2025-04-03 14:10:52 -05:00
Jose Martinez
7987fd1be7 Update bitbucket logger setup to use dynamic log level from configuration 2025-04-03 14:10:11 -05:00
Jose Martinez
db06a8e49e Update github logger setup to use dynamic log level from configuration 2025-04-03 14:09:11 -05:00
Jose Martinez
4fa2d82179 Set default log level to DEBUG in configuration and logger setup 2025-04-03 14:07:10 -05:00
ofir-frd
9254225949
fix: add error handling for missing review data in PR reviewer 2025-04-03 13:23:41 +03:00
sharoneyal
14971c4f5f
Add support for documentation content exceeding token limits (#1670)
* - Add support for documentation content exceeding token limits via two phase operation:
1. Ask LLM to rank headings which are most likely to contain an answer to a user question
2. Provide the corresponding files for the LLM to search for an answer.

- Refactor of help_docs to make the code more readable
- For the purpose of getting canonical path: git providers to use default branch and not the PR's source branch.
- Refactor of token counting and making it clear on when an estimate factor will be used.

* Code review changes:
1. Correctly handle exception during retry_with_fallback_models (to allow fallback model to run in case of failure)
2. Better naming for default_branch in bitbucket cloud provider
2025-04-03 11:51:26 +03:00
mrT23
3b0225544a
Fix code example in PR reviewer prompts to correctly show added line 2025-04-02 08:23:01 +03:00
Jose Martinez
dbfc07ccc1 Update logging configuration to use dynamic log level from settings 2025-04-01 15:54:51 -05:00
Tal
e692735b7b
Merge pull request #1662 from qodo-ai/tr/more_protections
Tr/more protections gitlab
2025-03-31 14:02:33 +03:00
mrT23
20cb139161
Improve code suggestion prompt to clarify handling of partial code segments in PR reviews 2025-03-31 08:39:40 +03:00
mrT23
afa4adcb23
Improve code analysis instructions for handling partial code blocks in PR reviews 2025-03-30 09:00:45 +03:00
mrT23
7bd0fefee4
Fix GitLab protections function and return value in PR questions 2025-03-29 19:53:46 +03:00
mrT23
02d9aed7fe
Fix GitLab provider to use default branch instead of target branch for repo settings 2025-03-29 19:39:56 +03:00
mrT23
7d47bd5f5e
Add GitLab protections to prevent quick actions in PR questions 2025-03-29 19:35:39 +03:00
mrT23
ddf94c14a3
Add configuration option for PR Code Suggestions to control publishing when no suggestions found 2025-03-29 09:33:31 +03:00
Eyal Sharon
e422f50cfe Fix for bug in get_canonical_url_parts when a new issue created, without git url provided. 2025-03-27 17:29:02 +02:00
Eyal Sharon
991a866368 documents' link generation: Make sure prefix ends with '/' 2025-03-26 21:58:15 +02:00
Eyal Sharon
255e1d0fc1 Missing class member 2025-03-26 14:29:50 +02:00
Eyal Sharon
7117e9fe0e Github Provider: Support publishing a comment on a non pr issue 2025-03-26 13:36:37 +02:00
Tal
6f6595c343
Merge pull request #1634 from ishaansehgal99/main
fix: Logging and Commenting
2025-03-26 07:51:24 +02:00
Ishaan Sehgal
b300cfa84d
Improve error logging with artifacts 2025-03-25 22:49:24 -07:00
Eyal Sharon
605eef64e7 Generate git url correctly in case invoked from both user and GitHub app contexts 2025-03-25 12:08:00 +02:00
Eyal Sharon
b161672218 Remove redundant abstractmethod for _prepare_clone_url_with_token 2025-03-24 15:56:45 +02:00
Eyal Sharon
5bc253e1d9 Add token count estimation factor to config 2025-03-24 15:53:22 +02:00
Eyal Sharon
8495e4d549 More comprehensive handling in count_tokens(force_accurate==True): In case model is neither OpenAI nor Anthropic Claude, simply use an elbow room factor in order to force a more conservative estimate. 2025-03-24 15:47:35 +02:00
Eyal Sharon
fb324d106c Remove non implemented method _prepare_clone_url_with_token from providers which don't support it and instead, issue a warning in base class. 2025-03-24 14:06:06 +02:00
Eyal Sharon
a4387b5829 Fix more /improve suggestions 2025-03-24 11:19:23 +02:00
Eyal Sharon
477ebf4926 Code recommendations from /improve 2025-03-24 10:54:50 +02:00
Eyal Sharon
e14fc7e02d Fix missing self.bearer_token for bitbucket related providers 2025-03-24 10:21:23 +02:00
Eyal Sharon
1bd65934df Merge origin/main into es/help_docs 2025-03-23 20:04:58 +02:00
Eyal Sharon
88a17848eb - Documentation
- Better error handling in case could not deduce repo url
2025-03-23 20:04:33 +02:00
Eyal Sharon
dd80276f3f Support cloning repo
Support forcing accurate token calculation (claude)
Help docs: Add desired branch in case of user supplied git repo, with default set to "main"
Better documentation for getting canonical url parts
2025-03-23 09:55:58 +02:00
cdornano
e925f31ac0
Update azuredevops_provider.py
Will make qodo agent comments "Active" by default, and not "ByDesign" which is renders to "unknown" on Azure DevOps PRs. With this, PR authors are obliged to treat the PR comment of the qodo agent before Merging. This will help companies in analysing the impact of qodo agent on their PR, as every comment needs to be treated as either "Resolved" "Won't fix" "Close"
2025-03-21 12:57:03 +00:00
Eyal Sharon
5e7e353670 Added help_docs feature. 2025-03-20 23:48:01 +02:00
ishaansehgal99
52d4312c9a fix: Logging and Commenting 2025-03-20 13:59:43 -07:00
Ishaan Sehgal
8ec6067b26
Merge branch 'qodo-ai:main' into main 2025-03-20 13:57:46 -07:00
ishaansehgal99
bc575e5a67 fix: Logging and Commenting 2025-03-20 13:55:07 -07:00
mrT23
b087458e33
Merge remote-tracking branch 'origin/main' 2025-03-20 21:49:27 +02:00
mrT23
6610921bba
cleanup 2025-03-20 21:49:19 +02:00
Ikko Eltociear Ashimine
fa77828db2
chore: update pr_reviewer_prompts.toml
minor fix
2025-03-18 03:52:36 +09:00
mrT23
1724a65ab2
docs: remove similar issues tool from documentation 2025-03-16 08:58:02 +02:00
mrT23
29e28056db
refactor: move response_language config to group with other language settings 2025-03-15 09:58:20 +02:00
mrT23
507cd6e675
skip in PR config 2025-03-15 09:56:57 +02:00
mrT23
f5e381e1b2
Add fallback for YAML parsing using original response text 2025-03-11 17:11:10 +02:00
mrT23
2cacaf56b0
Reduce collapsible_file_list_threshold from 8 to 6 2025-03-11 17:08:26 +02:00
mrT23
9a574e0caa
Add filter for files with bad extensions in language handler 2025-03-11 17:03:05 +02:00
mrT23
0f33750035
Remove unused filter_bad_extensions function and rename diff_files_original to diff_files 2025-03-11 16:56:41 +02:00
mrT23
4713175fcf
Update code suggestion evaluation criteria and line number descriptions 2025-03-11 16:50:42 +02:00
mrT23
d16012a568
Add decoupled and non-decoupled modes for code suggestions 2025-03-11 16:46:53 +02:00
mrT23
f5bd98a3b9
Add check for auto-generated files in language handler 2025-03-11 14:37:45 +02:00
Kenny Dizi
ffefcb8a04 Fix default value for extended_thinking_max_output_tokens 2025-03-11 17:48:12 +07:00
mrT23
35bb2b31e3
feat: add enable_comment_approval to encoded forbidden args 2025-03-10 12:10:19 +02:00
Tal
20d709075c
Merge pull request #1613 from qodo-ai/hl/update_auto_approve_docs
docs: update auto-approval documentation with clearer configuration
2025-03-10 11:56:48 +02:00
Tal
52c99e3f7b
Merge pull request #1605 from KennyDizi/main
Support extended thinking for model `claude-3-7-sonnet-20250219`
2025-03-09 17:03:37 +02:00
Hussam.lawen
884b49dd84
Add encoded: enable_manual_approval 2025-03-09 17:01:04 +02:00
Kenny Dizi
222155e4f2 Optimize logging 2025-03-08 08:53:29 +07:00
Kenny Dizi
f9d5e72058 Move logic to _configure_claude_extended_thinking 2025-03-08 08:35:34 +07:00
Tal
2619ff3eb3
Merge pull request #1612 from congziqi77/main
fix: repeat processing files to ignore
2025-03-07 21:08:46 +02:00
Tal
15e8167115
Update configuration.toml 2025-03-07 18:22:26 +02:00
Kenny Dizi
a8935dece3 Using 2048 for extended_thinking_budget_tokens as well as extended_thinking_max_output_tokens 2025-03-07 17:27:56 +07:00
congziqi
fd12191fcf fix: repeat processing files to ignore 2025-03-07 09:11:43 +08:00
muhammad-asn
4f2551e0a6 feat: add DeepInfra support 2025-03-06 15:49:07 +07:00
mrT23
4c0e371238
fix: validate one-liner suggestions to prevent repeating existing code 2025-03-06 08:18:52 +02:00
Kenny Dizi
30bf7572b0 Validate extended thinking parameters 2025-03-03 18:44:26 +07:00
Kenny Dizi
440d2368a4 Set temperature to 1 when using extended thinking 2025-03-03 18:30:52 +07:00
Kenny Dizi
215c10cc8c Add thinking block to request parameters 2025-03-03 18:29:33 +07:00
Kenny Dizi
7623e1a419 Removed trailing spaces 2025-03-03 18:23:45 +07:00
Kenny Dizi
5e30e190b8 Define models that support extended thinking feature 2025-03-03 18:22:31 +07:00
Kenny Dizi
5447dd2ac6 Add support claude extended thinking configurations 2025-03-03 18:21:57 +07:00
atsushi-ishibashi
8e6267b0e6 chore: bedrock/us.anthropic.claude-3-7-sonnet-20250219-v1:0 2025-03-02 08:44:23 +09:00
mrT23
7cf521c001
fix: improve null safety in GitLab webhook handler 2025-02-27 11:53:11 +02:00
mrT23
8182a4afc0
docs: update default model to o3-mini and improve language configuration instructions 2025-02-27 11:06:31 +02:00
mrT23
3817aa2868
fix: remove redundant temperature logging in litellm handler 2025-02-27 10:55:01 +02:00
mrT23
94a8606d24
fix: update default configuration values for publishing and verbosity 2025-02-27 10:52:20 +02:00
mrT23
af635650f1
fix: improve response language handling and configuration documentation 2025-02-27 10:50:28 +02:00